Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 848  83 909 966 961 470 318 343  37 360 750 484 594 342 722 429 312 143 804 886
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 429 342 848  83 886 484 312 909 470  NA  37 722 750 360 594 961 143 343 966  NA  NA 318 804
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 5 4 2 1 4 3 1 5 4 1
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "s" "c" "j" "g" "h" "H" "T" "A" "R" "N"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1] 3 4 5
which( manyNumbersWithNA > 900 )
[1]  8 16 19
which( is.na( manyNumbersWithNA ) )
[1] 10 20 21

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 909 966 961
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 909 966 961
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 909 966 961

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "H" "T" "A" "R" "N"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "s" "c" "j" "g" "h"
manyNumbers %in% 300:600
 [1] FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE  TRUE FALSE  TRUE FALSE  TRUE  TRUE  TRUE FALSE  TRUE  TRUE FALSE FALSE FALSE
which( manyNumbers %in% 300:600 )
[1]  6  7  8 10 12 13 14 16 17
sum( manyNumbers %in% 300:600 )
[1] 9

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "small" "small" "large" "small" "large" "small" "small" "large" "small" NA      "small" "large" "large" "small" "large" "large" "small" "small" "large" NA     
[21] NA      "small" "large"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "small"   "small"   "large"   "small"   "large"   "small"   "small"   "large"   "small"   "UNKNOWN" "small"   "large"   "large"   "small"   "large"   "large"  
[17] "small"   "small"   "large"   "UNKNOWN" "UNKNOWN" "small"   "large"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]   0   0 848   0 886   0   0 909   0  NA   0 722 750   0 594 961   0   0 966  NA  NA   0 804

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 5 4 2 1 3
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  5  4  2  1  3
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE FALSE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 19
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 966
which.min( manyNumbersWithNA )
[1] 11
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 37
range( manyNumbersWithNA, na.rm = TRUE )
[1]  37 966

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 429 342 848  83 886 484 312 909 470  NA  37 722 750 360 594 961 143 343 966  NA  NA 318 804
sort( manyNumbersWithNA )
 [1]  37  83 143 312 318 342 343 360 429 470 484 594 722 750 804 848 886 909 961 966
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  37  83 143 312 318 342 343 360 429 470 484 594 722 750 804 848 886 909 961 966  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 966 961 909 886 848 804 750 722 594 484 470 429 360 343 342 318 312 143  83  37  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 429 342 848  83 886
order( manyNumbersWithNA[1:5] )
[1] 4 2 1 3 5
rank( manyNumbersWithNA[1:5] )
[1] 3 2 4 1 5
sort( mixedLetters )
 [1] "A" "c" "g" "h" "H" "j" "N" "R" "s" "T"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1]  5.5 10.0  8.0  8.0  3.0  5.5  1.0  8.0  3.0  3.0
rank( manyDuplicates, ties.method = "min" )
 [1]  5 10  7  7  2  5  1  7  2  2
rank( manyDuplicates, ties.method = "random" )
 [1]  6 10  8  7  4  5  1  9  2  3

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.00000000 -0.50000000  0.00000000  0.50000000  1.00000000 -0.12088993  1.80206698  0.01255969  0.68982832 -0.74279084  0.25990219 -1.10382097 -1.05037770
[14]  0.46509616  1.32102216
round( v, 0 )
 [1] -1  0  0  0  1  0  2  0  1 -1  0 -1 -1  0  1
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0 -0.1  1.8  0.0  0.7 -0.7  0.3 -1.1 -1.1  0.5  1.3
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00 -0.12  1.80  0.01  0.69 -0.74  0.26 -1.10 -1.05  0.47  1.32
floor( v )
 [1] -1 -1  0  0  1 -1  1  0  0 -1  0 -2 -2  0  1
ceiling( v )
 [1] -1  0  0  1  1  0  2  1  1  0  1 -1 -1  1  2

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2022 Biomedical Data Sciences (BDS) | LUMC